INDEX

Explanations

references to geographical features and water bodies

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyTitle

-0.77

 NSCoder

-0.67

contentLoaded

-0.67

 المعيارى

-0.65

 للمعارف

-0.64

BeginContext

-0.64

Демографія

-0.63

 חיצוניים

-0.62

 विश्वसनीयता

-0.59

sidemargin

-0.57

POSITIVE LOGITS

 river

1.80

 stream

1.59

river

1.50

 River

1.48

River

1.43

 RIVER

1.40

 downstream

1.40

 rivers

1.33

 upstream

1.32

stream

1.32

Activations Density 0.199%

references to geographical features and water bodies

No Comments

No Known Activations